token.app › Compare › R1 vs GLM 5.2

R1 vs GLM 5.2

GLM 5.2 leads on 2 of 2 shared benchmarks. GLM 5.2 is 3.0× cheaper per token on a blended 3:1 basis. GLM 5.2 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
R1GLM 5.2
ProviderDeepSeekZhipu AI
Input $/1M$0.700$0.252
Output $/1M$2.50$0.792
Blended $/1M$1.15$0.387
Context window164K1.0M
Max output16K128K
ReleasedJan 2025Jun 2026
LicenceOpen weightsOpen weights
GPQA Diamond 71.7% 91.9%
OTIS Mock AIME 53.3% 86.4%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose R1 if…
  • No clear advantage on the data we hold.
Choose GLM 5.2 if…
  • Costs less per token — $0.387 vs $1.15 blended
  • Higher GPQA Diamond (91.9% vs 71.7%)
  • Higher OTIS Mock AIME (86.4% vs 53.3%)
  • Larger context window (1.0M)
  • Newer model (released Jun 2026)
FAQ
Which is better, R1 or GLM 5.2?
Across the 2 benchmarks both models have independently-run scores for, R1 leads on 0 and GLM 5.2 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is R1 cheaper than GLM 5.2?
GLM 5.2 is cheaper: $0.387 versus $1.15 per million tokens blended at 3:1 input:output. Input alone: $0.700 vs $0.252. Output alone: $2.50 vs $0.792.
What context windows do R1 and GLM 5.2 have?
R1: 163,840 tokens. GLM 5.2: 1,048,576 tokens.
Who makes R1 and GLM 5.2?
R1 is made by DeepSeek. GLM 5.2 is made by Zhipu AI.
Related comparisons